Follow
Tanmay Gangwani
Title
Cited by
Cited by
Year
Learning self-imitating diverse policies
T Gangwani, Q Liu, J Peng
arXiv preprint arXiv:1805.10309, 2018
492018
Policy optimization by genetic distillation
T Gangwani, J Peng
arXiv preprint arXiv:1711.01012, 2017
44*2017
State-only Imitation with Transition Dynamics Mismatch
T Gangwani, J Peng
arXiv preprint arXiv:2002.11879, 2020
362020
Learning belief representations for imitation learning in pomdps
T Gangwani, J Lehman, Q Liu, J Peng
Uncertainty in Artificial Intelligence, 1061-1071, 2020
242020
CASPAR: breaking serialization in lock-free multicore synchronization
T Gangwani, A Morrison, J Torrellas
ACM SIGARCH Computer Architecture News 44 (2), 789-804, 2016
142016
Learning Guidance Rewards with Trajectory-space Smoothing
T Gangwani, Y Zhou, J Peng
Advances in Neural Information Processing Systems 33, 2020
132020
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
M Wan, T Gangwani, J Peng
arXiv preprint arXiv:2006.07041, 2020
92020
Harnessing distribution ratio estimators for learning agents with quality and diversity
T Gangwani, J Peng, Y Zhou
Conference on Robot Learning, 2206-2215, 2021
72021
Hindsight Foresight Relabeling for Meta-Reinforcement Learning
M Wan, J Peng, T Gangwani
arXiv preprint arXiv:2109.09031, 2021
32021
Snug: architectural support for relaxed concurrent priority queueing in chip multiprocessors
A Heidarshenas, T Gangwani, S Yesil, A Morrison, J Torrellas
Proceedings of the 34th ACM International Conference on Supercomputing, 1-13, 2020
32020
Distributed and Secure ML with Self-tallying Multi-party Aggregation
Y Long, T Gangwani, H Mughees, C Gunter
arXiv preprint arXiv:1811.10296, 2018
22018
Imitation Learning from Observations under Transition Model Disparity
T Gangwani, Y Zhou, J Peng
arXiv preprint arXiv:2204.11446, 2022
12022
Reinforcement learning with supervision beyond environmental rewards
T Gangwani
University of Illinois at Urbana-Champaign, 2021
2021
Partial Redundancy Elimination using Lazy Code Motion
S Dasgupta, T Gangwani
arXiv preprint arXiv:1905.08178, 2019
2019
Breaking serialization in lock-free multicore synchronization
T Gangwani
2016
Accelerating Deterministic Replay
Y Shalabi, M Yan, T Gangwani
2014
Graph Coloring Using State Space Search
S Dasgupta, T Gangwani, M Yan, N Singh
The system can't perform the operation now. Try again later.
Articles 1–17